Popular repositories Loading

1. tiny_RAG tiny_RAG Public

   OneTinyRAG 是轻量可插拔的检索增强生成（RAG）框架：支持 BM25+Dense 混合检索、FAISS 向量索引、多分块策略与多格式文档处理；提供 DeepSeek API/本地 Ollama 双通道生成与 FastAPI 服务，配置驱动，易扩展。

   Python 2

2. NVSentinel NVSentinel Public

   Forked from NVIDIA/NVSentinel

   NVSentinel detects and remediates GPU faults on Kubernetes nodes

   Go 1

3. api api Public

   Forked from kai-scheduler/api

   Client facing APIs for KAI-Scheduler

   Go 1

4. KAI-Scheduler KAI-Scheduler Public

   Forked from kai-scheduler/KAI-Scheduler

   KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale

   Go 1

5. uccl uccl Public

   Forked from uccl-project/uccl

   UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

   C++ 1

6. llm-d-router llm-d-router Public

   Forked from llm-d/llm-d-router

   llm-d Router: The intelligent entry point for inference requests

   Go 1